© 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. 2150
    Prev
    Next
    INDEX
    Explanations

    finding new things

    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
    ellees
    -0.60
     consultato
    -0.60
    Cyfeiriadau
    -0.59
    省市镇
    -0.58
    mények
    -0.58
     Comprometido
    -0.58
     nakalista
    -0.57
    adaptiveStyles
    -0.57
     sécher
    -0.57
     CWE
    -0.55
    POSITIVE LOGITS
    Xna
    0.52
     chest
    0.51
    DrawerLayout
    0.45
     drawer
    0.45
     deepest
    0.42
     onAnimation
    0.42
     pleasure
    0.41
    getItemId
    0.41
     corners
    0.41
    MLLoader
    0.40
    Activations Density 0.011%

    No Known Activations