© 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. 5418
    Prev
    Next
    INDEX
    Explanations

    Dates

    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
    minecraft
    -0.52
    glBind
    -0.52
     désolés
    -0.50
     ComVisible
    -0.47
    Downloads
    -0.47
    ínsula
    -0.46
     yii
    -0.45
    riezmann
    -0.45
    PostExecute
    -0.44
    turnstile
    -0.44
    POSITIVE LOGITS
    fjspx
    0.77
     betweenstory
    0.72
    ]]);
    0.69
    sidemargin
    0.69
     nonUne
    0.68
     kaarangay
    0.66
     كومونز
    0.65
    "]));
    0.64
    ++]=
    0.61
    AutoScaleMode
    0.60
    Activations Density 0.010%

    No Known Activations