© 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. 5-CLT-HP
    7. 97769
    Prev
    Next
    INDEX
    Explanations

    descriptions

    np_max-act · 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
     large
    -0.63
     Large
    -0.54
    Large
    -0.53
    large
    -0.53
     grande
    -0.52
     LARGE
    -0.47
     wide
    -0.47
     gynhyrchwyd
    -0.46
     O
    -0.46
     broad
    -0.44
    POSITIVE LOGITS
     quæ
    0.79
     beſt
    0.77
     hivyo
    0.77
     myſelf
    0.76
    AndEndTag
    0.73
     purpoſe
    0.73
     juſt
    0.72
     Reſ
    0.72
    ArgsConstructor
    0.68
     ſtate
    0.68
    Activations Density 0.003%

    No Known Activations