© 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. 0-CLT-HP
    7. 94203
    Prev
    Next
    INDEX
    Explanations

    methods or techniques

    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
    Personensuche
    -0.81
    omeness
    -0.69
     nakalista
    -0.63
    UnknownFieldSet
    -0.61
     this
    -0.58
    WithIOException
    -0.56
    ьаж
    -0.54
    jago
    -0.54
    usermodel
    -0.53
     @"/
    -0.53
    POSITIVE LOGITS
    WebMethod
    0.58
    yntaxException
    0.54
    Sprintf
    0.54
    انجليز
    0.53
    ientôt
    0.50
    Ỏ
    0.49
    FileNotFound
    0.47
     forms
    0.46
    urlpatterns
    0.46
    
    0.46
    Activations Density 0.072%

    No Known Activations