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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97121
    Prev
    Next
    INDEX
    Explanations

    synth

    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
     itſelf
    -0.86
     raiſ
    -0.84
     uſed
    -0.82
     purpoſe
    -0.81
     Monfieur
    -0.80
     ſmall
    -0.76
     whoſe
    -0.75
     myſelf
    -0.74
     ſeveral
    -0.73
     Theſe
    -0.72
    POSITIVE LOGITS
    yntaxException
    0.78
    GraphicsUnit
    0.73
    enumii
    0.72
    WriteTagHelper
    0.72
    enumi
    0.68
     CreateTagHelper
    0.66
    bootstrapcdn
    0.65
    PostExecute
    0.63
    providedIn
    0.60
     Administrativna
    0.60
    Activations Density 0.243%

    No Known Activations