© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97060
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    الإنجليزية
    -0.74
    principalColumn
    -0.65
    UnusedPrivate
    -0.59
    ituary
    -0.59
     tartalomajánló
    -0.58
     transférez
    -0.57
    sist
    -0.56
    Jeografia
    -0.56
    LookAnd
    -0.52
     linkovi
    -0.52
    POSITIVE LOGITS
    TargetException
    0.58
    󠁿
    0.57
     Launch
    0.56
     CWE
    0.54
    Launch
    0.53
     ========
    0.52
     =======
    0.52
    Demografia
    0.52
     legales
    0.52
     launch
    0.51
    Activations Density 0.169%

    No Known Activations