© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 4940
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    ($__
    -0.52
    WriteLiteral
    -0.51
    <bos>
    -0.46
    甚
    -0.45
     these
    -0.45
    Autoritní
    -0.42
    imageshack
    -0.42
     whatever
    -0.41
     allt
    -0.41
     some
    -0.41
    POSITIVE LOGITS
     ModelExpression
    0.84
    });*/
    0.81
    };*/
    0.77
     disambiguazione
    0.74
    EDEFAULT
    0.73
    })*/
    0.73
    "]];
    0.72
    %");
    0.68
    Pautan
    0.67
    脚注の使い方
    0.67
    Activations Density 0.004%

    No Known Activations