© 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. 0-CLT-HP
    7. 94704
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
    Geplaatst
    -0.67
    nologue
    -0.59
     Normdatei
    -0.56
    ContentAlignment
    -0.56
    })));
    -0.56
    μως
    -0.55
     autorytatywna
    -0.54
    hdl
    -0.54
    imageshack
    -0.54
    CodeAttribute
    -0.54
    POSITIVE LOGITS
    таж
    0.62
     gynhyrchwyd
    0.59
     LUMP
    0.54
    exitRule
    0.52
    entlichen
    0.52
    AuthProvider
    0.50
    principalColumn
    0.49
    kömm
    0.49
    Géographie
    0.48
    actéristique
    0.48
    Activations Density 0.195%

    No Known Activations