© 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. 1-CLT-HP
    7. 12278
    Prev
    Next
    INDEX
    Explanations

    the

    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
    <bos>
    -0.63
     كومونز
    -0.61
    ukone
    -0.52
    contentLoaded
    -0.51
     “
    -0.47
    довлет
    -0.47
     rest
    -0.47
    ecake
    -0.47
    anthene
    -0.46
    □
    -0.44
    POSITIVE LOGITS
     estekak
    0.93
    TemporalType
    0.79
    CloseOperation
    0.72
    +#+#
    0.66
     <>",
    0.63
     Roskov
    0.63
    tvguidetime
    0.59
     FetchType
    0.58
    VersionUID
    0.58
    sidemargin
    0.57
    Activations Density 0.101%

    No Known Activations