© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 95169
    Prev
    Next
    INDEX
    Explanations

    Research and technical texts

    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
    KindOfClass
    -0.66
     conflits
    -0.59
     tartalomajánló
    -0.57
    typeof
    -0.53
     chinoise
    -0.51
     Catania
    -0.50
     tslint
    -0.50
     Meksika
    -0.49
     réunions
    -0.49
     čierna
    -0.48
    POSITIVE LOGITS
    مصادر
    0.71
    abetes
    0.65
    //
    0.63
     createState
    0.60
    #
    0.56
    แป
    0.56
    hards
    0.56
    хьтан
    0.55
    getExternal
    0.54
    蜓
    0.54
    Activations Density 0.000%

    No Known Activations