© 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. 4-CLT-HP
    7. 240
    Prev
    Next
    INDEX
    Explanations

    equals sign

    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
    ;
    -0.61
    ,
    -0.52
    .
    -0.45
    occo
    -0.44
    ;,
    -0.44
    :
    -0.43
    ↵↵
    -0.42
     which
    -0.42
    eden
    -0.42
     on
    -0.41
    POSITIVE LOGITS
    rungsseite
    0.92
    providedIn
    0.90
    цездатний
    0.89
    Rüyada
    0.88
     Theſe
    0.83
    })*/
    0.82
    featureID
    0.82
    AndEndTag
    0.81
    OGND
    0.81
    Koordinaten
    0.80
    Activations Density 0.029%

    No Known Activations