© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 2243
    Prev
    Next
    INDEX
    Explanations

    number

    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
    DockStyle
    -0.69
    цездатний
    -0.52
    __":
    
    -0.49
     TType
    -0.48
    \{\\
    -0.47
    ]^{-
    -0.47
     mínimos
    -0.47
    pektrum
    -0.47
    profitable
    -0.46
    ámenes
    -0.45
    POSITIVE LOGITS
    WebElementEntity
    0.63
     that
    0.61
     representing
    0.60
     describing
    0.60
     known
    0.58
     expressing
    0.56
    CPtr
    0.56
    .
    0.56
     arrived
    0.55
    MLLoader
    0.55
    Activations Density 0.002%

    No Known Activations