© 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. 5-CLT-HP
    7. 5395
    Prev
    Next
    INDEX
    Explanations

    code/technical writing

    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
    specialchars
    -0.68
     متعلقه
    -0.57
    を抱
    -0.53
    Билгалдахарш
    -0.52
    ngdoc
    -0.51
    Tikang
    -0.50
    BuildContext
    -0.49
     שוליים
    -0.49
     indag
    -0.49
    OGND
    -0.48
    POSITIVE LOGITS
    maier
    0.60
    "}";
    0.57
    bitat
    0.52
     chofe
    0.52
     Eindruck
    0.51
    '},
    0.51
     ſtate
    0.50
    انيف
    0.50
    endroit
    0.49
    ropoda
    0.49
    Activations Density 0.001%

    No Known Activations