© 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. 4-CLT-HP
    7. 3294
    Prev
    Next
    INDEX
    Explanations

    single-digit numbers

    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
    achite
    -0.54
     AudioClip
    -0.54
     utafitiHapana
    -0.53
    nibus
    -0.52
    MethodManager
    -0.52
    kloped
    -0.51
    ρίες
    -0.50
    MatButtonModule
    -0.47
    itiers
    -0.47
    ASSOCI
    -0.46
    POSITIVE LOGITS
    HtmlAttribute
    0.55
    IMPORTED
    0.55
     Roskov
    0.53
    Vidite
    0.52
     cavalli
    0.48
     Delegation
    0.47
    estacks
    0.47
    liferay
    0.47
    MessageState
    0.47
    Népesség
    0.46
    Activations Density 0.002%

    No Known Activations