© 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. 1069
    Prev
    Next
    INDEX
    Explanations

    React

    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
     تانيه
    -0.49
    новништво
    -0.47
     bine
    -0.45
     αυτο
    -0.40
    ANEOUS
    -0.40
    -
    -0.40
    ToMany
    -0.39
    OptionsMenu
    -0.39
     vell
    -0.39
     oscillatory
    -0.38
    POSITIVE LOGITS
     Winaray
    0.66
    nocache
    0.64
    ServiceException
    0.61
    WriteBarrier
    0.60
    Geplaatst
    0.60
     }}"
    0.59
     whoſe
    0.58
    ]-->
    0.58
    󠁿
    0.57
    "}},
    0.57
    Activations Density 0.000%

    No Known Activations