© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 2718
    Prev
    Next
    INDEX
    Explanations

    the frequency and context of the term "host" in relation to biological or computational contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jira
    -0.76
     jurídica
    -0.69
     Gente
    -0.69
    McLaren
    -0.69
    fication
    -0.68
     ALR
    -0.68
    StringField
    -0.67
     awakeFromNib
    -0.66
     scio
    -0.65
     Lega
    -0.64
    POSITIVE LOGITS
     HOST
    1.61
     hosts
    1.55
     Hosts
    1.55
     Host
    1.55
     host
    1.43
    HOST
    1.41
    Hosts
    1.39
    Host
    1.31
    hosts
    1.25
     Hosting
    1.21
    Activations Density 0.051%

    No Known Activations