© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97159
    Prev
    Next
    INDEX
    Explanations

    less/fewer

    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
    okovic
    -0.58
    TagMode
    -0.51
     labor
    -0.51
    []>(
    -0.51
    ɵɵ
    -0.51
     reward
    -0.50
    illaries
    -0.50
    versy
    -0.50
    entrée
    -0.49
    Vidite
    -0.49
    POSITIVE LOGITS
    DebuggerNonUser
    0.58
     bianchi
    0.56
     positifs
    0.53
    QMetaType
    0.53
    providedIn
    0.53
     than
    0.52
     Sandstone
    0.50
     decât
    0.49
     resourceCulture
    0.48
     réinitial
    0.48
    Activations Density 0.004%

    No Known Activations