© 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. 0-RES-MATRYOSHKA-DC
    7. 11445
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'alter' in various forms

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beginnetje
    -0.71
     cherry
    -0.58
     ally
    -0.57
    pædia
    -0.54
     Marzo
    -0.52
     Wegen
    -0.52
     Cherry
    -0.51
    íí
    -0.51
    WebElementEntity
    -0.50
    ovanie
    -0.50
    POSITIVE LOGITS
    ALTER
    2.63
    alter
    2.52
    Alter
    1.92
     Alter
    1.74
     ALTER
    1.41
     AssemblyTitle
    0.63
    initWithFrame
    0.61
    <tfoot>
    0.57
     devote
    0.56
    onViewCreated
    0.55
    Activations Density 0.001%

    No Known Activations