© 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. 1-CLT-HP
    7. 9145
    Prev
    Next
    INDEX
    Explanations

    level

    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
     oreilles
    -0.60
     dieux
    -0.58
     sabbia
    -0.56
     réfrig
    -0.56
     réguli
    -0.55
     lèvres
    -0.52
     partecipazione
    -0.52
     démocr
    -0.51
     nuages
    -0.51
     récompenses
    -0.51
    POSITIVE LOGITS
     nakalista
    0.96
    EndContext
    0.76
    Personendaten
    0.72
    NameInMap
    0.71
    UnusedPrivate
    0.68
    WebVitals
    0.68
    OGND
    0.68
     فريبيس
    0.67
    CloseOperation
    0.63
    TypedDataSet
    0.63
    Activations Density 0.017%

    No Known Activations