© 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. 5-CLT-HP
    7. 96065
    Prev
    Next
    INDEX
    Explanations

    not

    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
     "..\..\
    -0.83
     "..\..\..\
    -0.77
    CppMethod
    -0.68
    AndEndTag
    -0.62
    PhysRevD
    -0.60
    Kjelder
    -0.59
     continúas
    -0.59
    quations
    -0.58
    toolStripButton
    -0.57
    findpost
    -0.56
    POSITIVE LOGITS
    ,
    0.55
     unless
    0.51
     فريبيس
    0.49
    ftagPool
    0.49
     shouldn
    0.48
    MongoClient
    0.47
    atchewan
    0.46
    RunWith
    0.44
     Unless
    0.43
     dép
    0.43
    Activations Density 0.005%

    No Known Activations