© 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. 5-CLT-HP
    4. 1220
    Prev
    Next
    INDEX
    Explanations

    of

    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
     Else
    -0.46
     „
    -0.46
    istern
    -0.44
     Fines
    -0.44
    ulis
    -0.43
     mixture
    -0.43
     Preferencias
    -0.42
    menn
    -0.42
     nuclei
    -0.42
     publisher
    -0.42
    POSITIVE LOGITS
    <bos>
    2.19
    expandindo
    0.73
     autorytatywna
    0.71
    Personensuche
    0.63
     AssemblyTitle
    0.62
    DockStyle
    0.61
    #
    0.59
     Савезне
    0.55
     itſelf
    0.54
    Geplaatst
    0.53
    Activations Density 0.025%

    No Known Activations