© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 92312
    Prev
    Next
    INDEX
    Explanations

    Use of "back" and conversational tone

    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
    UserScript
    -0.44
    setChecked
    -0.42
    vola
    -0.40
    ANNES
    -0.40
    ved
    -0.39
     chaired
    -0.38
    купа
    -0.37
    いな
    -0.36
     inventory
    -0.36
     forState
    -0.36
    POSITIVE LOGITS
     otomatig
    0.79
     Roskov
    0.75
    SourceChecksum
    0.73
    BeginContext
    0.71
     nahilalakip
    0.71
    CppMethod
    0.70
    TagMode
    0.69
     tartalomajánló
    0.68
    bootstrapcdn
    0.66
    nemies
    0.65
    Activations Density 0.000%

    No Known Activations