© 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. 93833
    Prev
    Next
    INDEX
    Explanations

    name origins

    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
    SequentialGroup
    -0.91
     ModelExpression
    -0.85
     Мексичка
    -0.84
    '],
    -0.83
    matchCondition
    -0.81
     createSlice
    -0.78
    Personendaten
    -0.77
     ComVisible
    -0.74
    "],
    -0.74
     Wikimedijinoj
    -0.74
    POSITIVE LOGITS
    jerg
    0.37
     come
    0.37
    Strike
    0.36
    bege
    0.36
     auszu
    0.36
    vergne
    0.35
     Montal
    0.35
     steps
    0.35
     signes
    0.35
    goog
    0.35
    Activations Density 0.004%

    No Known Activations