© 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. 20-CLT-HP
    7. 72903
    Prev
    Next
    INDEX
    Explanations

    code/technical texts

    np_max-act-logits · 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
    archiviato
    -0.65
    LookAnd
    -0.59
    localctx
    -0.58
     sanitaires
    -0.57
    Referencie
    -0.57
     Exactos
    -0.52
    Tikang
    -0.52
    Personendaten
    -0.50
    Geplaatst
    -0.50
    styl
    -0.50
    POSITIVE LOGITS
    CloseOperation
    0.69
    ArgumentParser
    0.53
    KommentareTeilen
    0.49
    ParallelGroup
    0.48
    SequentialGroup
    0.46
    tvguidetime
    0.45
    نیم
    0.44
     \<
    0.44
    bindingNavigator
    0.44
     sèche
    0.42
    Activations Density 0.000%

    No Known Activations