© 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. 1-CLT-HP
    7. 10936
    Prev
    Next
    INDEX
    Explanations

    ode

    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
    \"");
    -0.51
    nocache
    -0.50
    ngdoc
    -0.50
    obiology
    -0.48
    dg
    -0.48
    XmlAccessorType
    -0.47
    AddField
    -0.46
    abcdefghijklmnop
    -0.46
    Erreferentziak
    -0.45
    }');
    -0.44
    POSITIVE LOGITS
     الحره
    0.64
     Matka
    0.59
    vitis
    0.52
     Tats
    0.52
     intStringLen
    0.51
     Alvar
    0.51
     UTM
    0.50
    новниш
    0.49
    illige
    0.48
    FieldBuilder
    0.48
    Activations Density 0.012%

    No Known Activations