© 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. 0-CLT-HP
    7. 41357
    Prev
    Next
    INDEX
    Explanations

    &

    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
     and
    -0.54
    Is
    -0.47
    RemoteException
    -0.38
    щенко
    -0.36
    üdis
    -0.35
     cancerous
    -0.35
    othelioma
    -0.35
    ietic
    -0.35
     giugno
    -0.34
    .
    -0.34
    POSITIVE LOGITS
     jspb
    0.82
    ValueStyle
    0.79
    DebuggerNonUser
    0.79
    rungsseite
    0.77
     BoxFit
    0.77
     Reſ
    0.77
    SourceChecksum
    0.76
    GraphicsUnit
    0.76
     Anſ
    0.75
     Houſe
    0.74
    Activations Density 0.108%

    No Known Activations