© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1097
    Prev
    Next
    INDEX
    Explanations

    sta

    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
    :✨
    -0.74
     sta
    -0.69
    AndEndTag
    -0.68
     behind
    -0.67
    सन्दर्भ
    -0.63
     TA
    -0.62
    +:+
    -0.61
    Personensuche
    -0.60
    intios
    -0.59
     Sta
    -0.59
    POSITIVE LOGITS
    śmy
    0.46
    monton
    0.43
     âgées
    0.42
    AnchorStyles
    0.42
    yyah
    0.42
     picioare
    0.41
     MenuView
    0.40
    seamnă
    0.40
    Geplaatst
    0.38
    providedIn
    0.38
    Activations Density 0.047%

    No Known Activations