© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75919
    Prev
    Next
    INDEX
    Explanations

    IDS

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beginnetje
    -0.56
    mello
    -0.56
     Block
    -0.55
    agno
    -0.52
     Read
    -0.52
     onCreateView
    -0.52
     Gree
    -0.51
     Mag
    -0.51
    blox
    -0.51
    alto
    -0.51
    POSITIVE LOGITS
    Hozzáférés
    0.52
    IDS
    0.51
    @[+][
    0.47
     Monfieur
    0.47
     sapi
    0.46
    
    0.46
    IsMutable
    0.44
     IDS
    0.43
     Inſ
    0.42
     SIS
    0.41
    Activations Density 0.006%

    No Known Activations