© 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. 0-CLT-HP
    7. 91125
    Prev
    Next
    INDEX
    Explanations

    limitations and clarifications

    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
    IntoConstraints
    -0.82
     besök
    -0.67
     stessi
    -0.66
    __':
    -0.65
     mêmes
    -0.65
    AndEndTag
    -0.63
     nødvendig
    -0.60
     dieux
    -0.59
    __':
    -0.59
    例文帳に追加
    -0.59
    POSITIVE LOGITS
    +#+#
    0.71
    aarrggbb
    0.63
    flashdata
    0.58
     claims
    0.53
    VolleyError
    0.52
    ########.
    0.51
    MENAFN
    0.51
    Alike
    0.50
     stringBy
    0.49
     say
    0.49
    Activations Density 0.095%

    No Known Activations