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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 3471
    Prev
    Next
    INDEX
    Explanations

    risk

    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
    parency
    -0.48
    ApiModel
    -0.43
    Bibliograf
    -0.40
    retan
    -0.40
    AppMethodBeat
    -0.39
    groupId
    -0.39
     بتاريخ
    -0.39
    mMap
    -0.38
     MediatR
    -0.38
    PMG
    -0.38
    POSITIVE LOGITS
    CloseOperation
    0.73
    Referanser
    0.69
    <?
    0.66
    IndentedString
    0.66
    iempos
    0.62
    Referencie
    0.60
    ecap
    0.57
    Artigo
    0.56
    нительно
    0.55
     betweenstory
    0.55
    Activations Density 0.001%

    No Known Activations